app.py

import os
import requests 
requests.adapters.DEFAULT_TIMEOUT = 60

from dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv()) # read local .env file
hf_api_key = os.environ['HF_API_KEY']

# Helper function
import requests, json
from text_generation import Client


#FalcomLM-instruct endpoint on the text_generation library
URL = "https://api-inference.huggingface.co/models/HuggingFaceH4/zephyr-7b-beta"
client = Client(URL, timeout=120)

#Back to Lesson 2, time flies!
import gradio as gr
def generate(input, slider):
    output = client.generate(input, max_new_tokens=slider).generated_text
    return output

def format_chat_prompt(message, chat_history):
    prompt = ""
    for turn in chat_history:
        user_message, bot_message = turn
        prompt = f"{prompt}\nUser: {user_message}\nAssistant: {bot_message}"
    prompt = f"{prompt}\nUser: {message}\nAssistant:"
    return prompt

def respond(message, chat_history):
        formatted_prompt = format_chat_prompt(message, chat_history)
        bot_message = client.generate(formatted_prompt,
                                     max_new_tokens=1024,
                                     stop_sequences=["\nUser:", "<|endoftext|>"]).generated_text
        chat_history.append((message, bot_message))
        return "", chat_history



def loadGUI():
    with gr.Blocks() as demo:
        chatbot = gr.Chatbot(height=240) #just to fit the notebook
        msg = gr.Textbox(label="Prompt")
        btn = gr.Button("Submit")
        clear = gr.ClearButton(components=[msg, chatbot], value="Clear console")

        btn.click(respond, inputs=[msg, chatbot], outputs=[msg, chatbot])
        msg.submit(respond, inputs=[msg, chatbot], outputs=[msg, chatbot]) #Press enter to submit

        gr.close_all()
        demo.launch(share=True)
    
     
def main():
     loadGUI()
     
     
if __name__ == "__main__":
     main()